Adobe co-authored 21 papers at top audio conferences in 2021 – twelve papers at ICASSP, six at WASPAA and three at ISMIR – with topics ranging from high quality speech synthesis to cross-modal music retrieval, automatic optimization of DSP algorithms, few-shot audio recognition, HRTF modelling, and many more.
Three Adobe Research co-authored papers received awards at WASPAA 2021 and ISMIR 2021. Adobe researchers also served as chairs or committee members for all three conferences.
Nearly all of Adobe co-authored papers are the result of student internships or other collaborations with university students and faculty. Check out the Adobe Research Careers website to learn more about internships and full-time career opportunities.
ICASSP 2021 (June 5 – 11, 2021)
Bandwidth Extension Is All You Need Jiaqi Su, Yunyun Wang, Adam Finkelstein, Zeyu Jin CDPAM: Contrastive Learning for Perceptual Audio Similarity Pranay Manocha, Zeyu Jin, Richard Zhang, Adam Finkelstein Communication-Cost Aware Microphone Selection for Neural Speech Enhancement with Ad-Hoc Microphone Arrays Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis Context-Aware Prosody Correction For Text-Based Speech Editing Max Morrison, Lucas Rencker, Zeyu Jin, Nicholas Bryan, Juan-Pablo Caceres, Bryan Pardo Differentiable Signal Processing With Black-Box Audio Effects Marco Martınez Ramırez, Oliver Wang, Paris Smaragdis, Nicholas Bryan Few-Shot Continual Learning For Audio Classification Yu Wang, Nicholas Bryan, Mark Cartwright, Juan Pablo Bello, Justin Salamon LIFI: Towards Linguistically Informed Frame Interpolation Aradhya Neeraj Mathur, Devansh Batra, Yaman Kumar, Rajiv Ratn Shah, Roger Zimmermann, Changyou Chen Optimizing Short-Time Fourier Transform Parameters Via Gradient Descent An Zhao, Krishna Subramani, Paris Smaragdis Personalized HRTF Modeling Using DNN-augmented BEM Mengfan Zhang, Jui-Hsien Wang, Doug James Sound Event Detection And Separation: A Benchmark On DESED Synthetic Soundscapes Nicolas Turpault, Romain Serizel, Scott Wisdom, Hakan Erdogan, John Hershey, Eduardo Fonseca, Prem Seetharaman, Justin Salamon Unified Gradient Reweighting for Model Biasing with Applications to Source Separation Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis What’s All The Fuss About Free Universal Sound Separation Data? Scott Wisdom, Hakan Erdogan, Daniel Ellis, Romain Serizel, Nicolas Turpault, Eduardo Fonseca, Justin Salamon, Prem Seetharaman, John Hershey
WASPAA 2021 (October 17 – 20, 2021)
Auto-DSP: Learning to Optimize Acoustic Echo Cancellers Jonah Casebeer, Nicholas Bryan, Paris Smaragdis HiFi-GAN-2: Studio-quality speech enhancement via generative adversarial networks conditioned on acoustic features Jiaqi Su, Zeyu Jin, Adam Finkelstein Point Cloud Audio Processing Krishna Subramani, Paris Smaragdis Best Paper Award Separate but Together: Unsupervised Federated Learning for Speech Enhancement From Non-IID Data Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis Sound Event Detection With Adaptive Frequency Selection Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis Who Calls the Shots? Rethinking Few-Shot Learning for Audio Yu Wang, Nicholas Bryan, Justin Salamon, Mark Cartwright, Juan Pablo Bello Best Audio Few-Shot Learning Paper Award
ISMIR 2021 conference (November 8 – 12, 2021)
Controllable deep melody generation via hierarchical music representation Shuqi Dai, Zeyu Jin, Celso Gomes, Roger Dannenberg Deep Embeddings and Section Fusion Improve Music Segmentation Justin Salamon, Oriol Nieto, Nicholas Bryan Emotion Embedding Spaces for Matching Music to Stories Minz Won, Justin Salamon, Nicholas Bryan, Gautham Mysore, Xavier Serra Best Student Paper Award
